Publications
We publish our research in high-impact conferences and journals within the field of Computer Science. We have collaborated top IT tech companies such as AWS AI Labs, Google Research, and NAVER AI Lab.
As of now, we published more than 30 CS top confernces in various domains, including NLP (EMNLP), CV (ICCV, CVPR), ML (NeurIPS, ICLR, ICML, AAAI), DM (KDD, CIKM, ICDM, WWW, SIGMOD).
Asterisk (*) denotes corresponding authors.
2023
- Enhancing abstractiveness of summarization models through calibrated distillationIn Empirical Methods in Natural Language Processing, Findings, 2023
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel DecodingIn Empirical Methods in Natural Language Processing, Main, 2023
- Robust Data Pruning under Label Noise via Maximizing Re-labeling AccuracyIn Advances in Neural Information Processing Systems, 2023
- Generating Instance-level Prompts for Rehearsal-free Continual LearningIn International Conference on Computer Vision, 2023
- Context Consistency Regularization for Label Sparsity in Time SeriesIn International Conference on Machine Learning, 2023
- Re-thinking Federated Active Learning based on Inter-class DiversityIn International Conference on Computer Vision and Pattern Recognition, 2023
- Online Boundary-Free Continual Learning by Scheduled Data PriorIn International Conference on Learning Representation, 2023
- Data collection and quality challenges in deep learning: A data-centric ai perspectiveThe VLDB Journal, 2023
2022
- Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active LearningIn Advances in Neural Information Processing Systems, 2022
- Understanding cross-domain few-shot learning: An experimental studyIn Advances in Neural Information Processing Systems, 2022
- Multi-view POI-level Cellular Trajectory Reconstruction for Digital Contact Tracing of Infectious DiseasesIn International Conference on Data Mining, 2022
- FedRN: Exploiting k-Reliable Neighbors Towards Robust Federated LearningIn International Conference on Information and Knowledge Management, 2022
- e-clip: Large-scale vision-language representation learning in e-commerceIn International Conference on Information and Knowledge Management, 2022
- ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot LearningIn International Conference on Information and Knowledge Management, 2022
- Time Is MattEr: Temporal Self-supervision for Video TransformersIn International Conference on Machine Learning, 2022
- Dataset condensation via efficient synthetic-data parameterizationIn International Conference on Machine Learning, 2022
- Online continual learning on a contaminated data stream with blurry task boundariesIn International Conference on Computer Vision and Pattern Recognition, 2022
- TNNLSLearning from noisy labels with deep neural networks: A surveyIEEE Transactions on Neural Networks and Learning Systems, 2022
- Meta-learning for online update of recommender systemsIn AAAI Conference on Artificial Intelligence, 2022
- AAAI OralCovid-eenet: Predicting fine-grained impact of COVID-19 on local economiesIn AAAI Conference on Artificial Intelligence, 2022
2021
- Vidt: An efficient and effective fully transformer-based object detectorIn International Conference on Learning Representations, 2021
- Coherence-based label propagation over time series for accelerated active learningIn International Conference on Learning Representations, 2021
- BMVCExploiting scene depth for object detection with multimodal transformersIn British Machine Vision Conference, 2021
- Task-agnostic undesirable feature deactivation using out-of-distribution dataIn Advances in Neural Information Processing Systems, 2021
- Robust learning by self-transition for handling noisy labelsIn International Conference on Knowledge Discovery and Data Mining, 2021
- Machine learning robustness, fairness, and their convergenceIn International Conference on Knowledge Discovery and Data Mining, 2021
- Premere: Meta-reweighting via self-ensembling for point-of-interest recommendationIn AAAI Conference on artificial intelligence, 2021
2020
- Carpe Diem, Seize the Samples Uncertain" at the Moment" for Adaptive Batch SelectionIn International Conference on Information and Knowledge Management, 2020
- MLAda-boundary: accelerating DNN training via adaptive boundary batch selectionMachine Learning, 2020
- Hi-COVIDNet: Deep learning approach to predict inbound COVID-19 patients and case study in South KoreaIn International Conference on Knowledge Discovery and Data Mining, 2020
- PAKDDRevisit Prediction by Deep Survival AnalysisIn Pacific-Asia Conference on Knowledge Discovery and Data Mining, 2020
- TRAP: Two-level regularized autoencoder-based embedding for power-law distributed dataIn The Web Conference, 2020
2019
- Selfie: Refurbishing unclean samples for robust deep learningIn International Conference on Machine Learning, 2019
2018
- RP-DBSCAN: A superfast parallel DBSCAN algorithm based on random partitioningIn Special Interest Group on Management of Data, 2018
2017
- PAMAE: parallel k-medoids clustering with high accuracy and efficiencyIn International Conference on Knowledge Discovery and Data Mining, 2017